CN111179257A - Evaluation method and device, electronic equipment and storage medium - Google Patents

Evaluation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN111179257A
CN111179257A CN201911410488.4A CN201911410488A CN111179257A CN 111179257 A CN111179257 A CN 111179257A CN 201911410488 A CN201911410488 A CN 201911410488A CN 111179257 A CN111179257 A CN 111179257A
Authority
CN
China
Prior art keywords
operation result
result
standard
evaluation
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911410488.4A
Other languages
Chinese (zh)
Inventor
王策
贾洁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai United Imaging Healthcare Co Ltd
Original Assignee
Shanghai United Imaging Healthcare Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai United Imaging Healthcare Co Ltd filed Critical Shanghai United Imaging Healthcare Co Ltd
Priority to CN201911410488.4A priority Critical patent/CN111179257A/en
Publication of CN111179257A publication Critical patent/CN111179257A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30008—Bone
    • G06T2207/30012—Spine; Backbone
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30168—Image quality inspection

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

The embodiment of the invention discloses an evaluation method, an evaluation device, electronic equipment and a storage medium. Determining the operation result and the standard evaluation index of the current object, calculating the similarity value of the operation result and the standard evaluation index based on a preset similarity calculation formula, and determining the similarity value as the evaluation result of the operation result. The problem that in the prior art, evaluation takes more time due to the fact that the reliability of the operation result is judged through comparison of the output results of two algorithms is solved, the purpose that the evaluation result can be obtained through simple calculation according to the operation result and the standard evaluation index is achieved, and the effects of reducing the evaluation time and improving the timeliness are achieved.

Description

Evaluation method and device, electronic equipment and storage medium
Technical Field
The embodiments of the present invention relate to image quality evaluation technologies, and in particular, to an evaluation method and apparatus, an electronic device, and a storage medium.
Background
In the process of processing a medical image, because an individual difference exists between the shot objects and the processing scenes of various diseases are changeable, when the acquired medical image is processed by an image processing algorithm, the image processing algorithm is inevitably not suitable for some scenes, so that in order to ensure the accuracy of medical image processing, a doctor is generally required to evaluate the processed image after the processed medical image is acquired. However, the way that the doctor evaluates the processed image causes wrong evaluation due to carelessness or fatigue of the doctor, thereby causing some unnecessary problems in the following.
In contrast, in the prior art, the original volume data of the scanned object is generally input into two different algorithms respectively, and then the output results of the two algorithms are compared to judge the reliability of the operation result of the algorithm.
Disclosure of Invention
The embodiment of the invention provides an evaluation method, an evaluation device, electronic equipment and a storage medium, and aims to achieve the effect of improving evaluation efficiency.
In a first aspect, an embodiment of the present invention provides an evaluation method, where the evaluation method includes:
determining an operation result and a standard evaluation index of a current object;
calculating a similarity value of the operation result and the standard evaluation index based on a preset similarity calculation formula;
and determining the similarity value as an evaluation result of the operation result.
In a second aspect, an embodiment of the present invention further provides an evaluation apparatus, where the evaluation apparatus includes:
the first determination module is used for determining the operation result and the standard evaluation index of the current object;
the similarity value calculation module is used for calculating the similarity value of the operation result and the standard evaluation index based on a preset similarity calculation formula;
and the second determining module is used for determining the similarity value as the evaluation result of the operation result.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the evaluation method according to any one of the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present invention further provides a storage medium containing computer-executable instructions, where the computer-executable instructions, when executed by a computer processor, implement the evaluation method according to any one of the first aspect.
The technical scheme provided by the embodiment of the invention determines the operation result and the standard evaluation index of the current object, calculates the similarity value of the operation result and the standard evaluation index based on the preset similarity calculation formula, and determines the similarity value as the evaluation result of the operation result. The method solves the problem that the evaluation takes more time due to the fact that the reliability of the operation result is judged by comparing the output results of two algorithms in the prior art, achieves the purpose that the evaluation result can be obtained by simply calculating according to the operation result and the standard evaluation index, and achieves the effects of reducing the evaluation time and improving the timeliness
Drawings
Fig. 1 is a schematic flow chart of an evaluation method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of an evaluation method according to a second embodiment of the present invention;
FIG. 3 is a diagram illustrating an operation model according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of an evaluation apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a schematic flowchart of an evaluation method according to an embodiment of the present invention, where the embodiment is applicable to a case where an evaluation result is determined by comparing an operation result of a current object with a standard evaluation index, and the method may be executed by an evaluation apparatus, where the apparatus may be implemented by software and/or hardware and is generally integrated in a terminal or an electronic device. Referring specifically to fig. 1, the method may include the steps of:
and S110, determining the operation result and the standard evaluation index of the current object.
The current object may be understood as an object to be evaluated or a local area of the object to be evaluated. Illustratively, the object to be evaluated may be a human body, an animal body or some simulation experiment body, and the current object may be the spine, the chest cavity, the head, the limbs and the like of the object to be evaluated. The operation result may be understood as a positioning result of the current object, and may be position information of a region of interest of the current object determined by a detection means. For example, the current object is a C2 vertebral disc, the operation result may be original volume data of the C2 vertebral disc, the original volume data may be volume data obtained by detection means, such as image data obtained by detection means such as magnetic resonance, ultrasound, CT (Computed Tomography), and the like, the original volume data is input to a trained positioning model or positioning algorithm, so that the positioning result of the C2 vertebral disc may be obtained, and the positioning result of the C2 vertebral disc is taken as the operation result of the current object. It should be noted that the operation result may be, but is not limited to, position information of an organ such as a liver, a heart, a lung, or the like, or position information of a region of interest in the organ, a target positioning point, or a target segmentation point, or position information of a region of interest in a bone such as a vertebral disc, and is not limited to the vertebral disc for example, and the operation result may be obtained by processing original volume data of a current object through an operation rule or an operation model.
The standard evaluation index may be understood as gold standard data of a region of interest of the current object, or as a standard model or a standard template. For example, if the current subject is a spine, the standard assessment index may be gold standard data for any one of the discs of the spine (e.g., the C1 disc, the C2 disc, the C3 disc, etc.), wherein the C1 disc, the C2 disc, and the C3 disc may be referred to as a region of interest of the spine. It is understood that the standard evaluation index may be determined based on gold standard data of different subjects, for example, based on gold standard data of subjects of different ages, wherein the gold standard data of different subjects may be obtained by manual labeling or by historical detection data.
And S120, calculating a similarity value of the operation result and the standard evaluation index based on a preset similarity calculation formula.
Optionally, the preset similarity calculation formula may be:
Figure BDA0002349843940000041
wherein α is a normalization coefficient, dis (x, y) is an Euclidean distance calculation formula, i is a label index of a current object, N is the total number of the current object, prediFor the result of the operation of the feature point with index i for the index of the current object, modeliAnd (5) indexing the standard evaluation index of the characteristic point with i for the label of the current object.
The operation result and the standard evaluation index of the current object are determined according to the steps. Alternatively, the standard evaluation index may be determined according to the relative position of the relative feature point of the history object and the standard feature point established in advance. In order to ensure consistency of the operation result and the standard evaluation index, the operation result may include relative positions of the target feature point and the standard feature point of the current object; optionally, the standard evaluation index may also be determined according to a distance between adjacent feature points of the historical object, and accordingly, the operation result includes a distance between any two adjacent feature points of the current object.
Specifically, if the standard evaluation index is determined according to the relative position of the relative feature point of the historical object and the pre-established standard feature point, and the operation result includes the relative position of the target feature point of the current object and the standard feature point, then at this time, the preset similarity calculation formula pred is usediThe position coordinates of the feature point of index i may be the index of the current object. Illustratively, the data of the historical object includes a plurality of vertebral discs of the spine, each vertebral disc corresponding to a particular markerAnd specific positions, the C3 vertebral disc can be set as a standard characteristic point, the coordinates of the standard characteristic point are taken as coordinate origin points, then the position coordinates of other vertebral discs are respectively determined according to the relative positions of the other vertebral discs (such as C1, C2, C4, C5 and the like) and the standard characteristic point (C3), if the current object is the C2 vertebral disc, the standard evaluation index of the current object (namely, the standard position coordinates of the C2 vertebral disc) can be determined according to the relative positions of the C2 vertebral disc and the C3 vertebral disc, namely, the standard evaluation index of the C2 vertebral disc is determined to be the position coordinates of the C2 vertebral disc.
Specifically, if the standard evaluation index is determined according to the distance between adjacent feature points of the historical object, and the operation result includes the distance between any two adjacent feature points of the current object, at this time, the preset similarity calculation formula prediThe distance between a feature point with index i and an adjacent feature point for the index of the current object may be used. Illustratively, the data of the historical objects includes a plurality of discs of the spine, each disc corresponding to a particular marker and a particular location, respectively determining the distance between adjacent discs, e.g., determining the distance of the C1-C2 discs, the distance of the C2-C3 discs, the distance of the C3-C4 discs, the distance of the C4-C5 discs, etc. If the current object is the C2 disc, the standard evaluation index of the current object may be determined according to the distance between the C2 disc and the C1 disc of the current object, or according to the distance between the C2 disc and the C3 disc.
It should be noted that the similarity between the operation result and the standard evaluation index is not limited to be calculated according to the euclidean distance calculation formula, and may also be calculated in other manners, which is not specifically described in this embodiment.
And S130, determining the similar value as the evaluation result of the operation result.
In this embodiment, the evaluation result of the operation result is determined according to the similarity between the operation result and the standard evaluation index, where the evaluation result may be positively correlated with the similarity, and the higher the similarity is, the better the evaluation result is, and correspondingly, the lower the similarity is, the worse the evaluation result is.
The technical scheme provided by the embodiment of the invention determines the operation result and the standard evaluation index of the current object, calculates the similarity value of the operation result and the standard evaluation index based on the preset similarity calculation formula, and determines the similarity value as the evaluation result of the operation result. The problem that in the prior art, evaluation takes more time due to the fact that the reliability of the operation result is judged through comparison of the output results of two algorithms is solved, the purpose that the evaluation result can be obtained through simple calculation according to the operation result and the standard evaluation index is achieved, and the effects of reducing the evaluation time and improving the timeliness are achieved.
Example two
Fig. 2 is a schematic flow chart of an image evaluation method according to a second embodiment of the present invention. The technical scheme of the embodiment is refined on the basis of the embodiment. Optionally, the determining an operation result of the current object includes: acquiring original volume data of the current object; inputting the original volume data into a pre-trained operation model, and determining the operation result according to the output result of the operation model, wherein the operation model is obtained by training an initial network according to the standard volume data and the standard probability result of the current object. In the method, reference is made to the above-described embodiments for those parts which are not described in detail. Referring specifically to fig. 2, the method may include the steps of:
and S210, determining the standard evaluation index of the current object.
S220, acquiring the original volume data of the current object.
The original volume data can be understood as the original scan data of the current object. For example, by scanning the spine with a CT device, the raw volume data can be the data received by the detector for each vertebral disc.
And S230, inputting the original volume data into a pre-trained operation model, and determining an operation result according to an output result of the operation model.
The operation model can be obtained by training the initial network according to the standard body data and the standard probability result of the current object. Alternatively, the operation result may be obtained by: determining the number of output channels of the operation model and the output probability map of each channel, and determining an operation result based on the probability maps and a preset probability threshold. Optionally, after the probability map and the preset probability threshold are obtained, the pixel points exceeding the probability threshold in the probability map may be obtained, and the pixel point with the maximum probability value is determined as the operation result.
Fig. 3 is a schematic diagram of an operation model, and the method is explained by way of example with reference to fig. 3. Illustratively, the operational model is a deep convolutional neural network model, which may include an input module, a downsampling subnetwork, an upsampling subnetwork and an output module, and the input module, the downsampling subnetwork, the upsampling subnetwork and the output module may respectively include a plurality of convolution blocks, where a convolution block in the downsampling subnetwork is connected to a corresponding convolution block in the upsampling subnetwork laterally for transmitting a feature map of a convolution block in the downsampling subnetwork to a corresponding convolution block in the upsampling subnetwork, so as to implement fusion of feature information of different levels in the upsampling subnetwork, so that the feature information includes both profile information of a shallow level and detail information of a deep level, thereby improving accuracy of feature identification. Optionally, the convolution blocks of the input module, the down-sampling sub-network, the up-sampling sub-network, and the output module include at least one convolution layer, and at least one of an activation function, a normalization layer, and a pooling layer may be set after each convolution layer. Optionally, the downsampling subnetwork comprises a convolution in the form of a RELU activation function, the convolution kernel of which may be 2 x 2 in size, with a step size of 2; the upsampling subnetwork comprises deconvolution in the form of a RELU activation function, the size of a convolution kernel of the deconvolution can be 2 x 2, and the step size is 2; the input module and the output module include deconvolution in the form of a RELU activation function, the convolution kernel of which may be 3 x 3 in size with a step size of 1.
In the training stage of the operational model, standard body data of a plurality of vertebral discs such as a C1 vertebral disc, a C2 vertebral disc, a C3 vertebral disc and a C4 vertebral disc are input into an initial network, a probability map of the vertebral discs is output by multiple channels at the output end of the initial network, the number of channels of the initial network is determined by the number of the vertebral discs, and then the initial network is adjusted according to the probability map output by each channel and a standard probability result until the operational model is obtained. When the current vertebral disc (for example, the C2 vertebral disc and the C3 vertebral disc) is positioned by using the operation model, that is, the operation results of the C2 vertebral disc and the C3 vertebral disc are determined, the original volume data of the C2 vertebral disc and the C3 vertebral disc can be respectively input into the operation model, the operation model respectively outputs the probability maps of the C2 vertebral disc and the C3 vertebral disc through two channels, a pixel point with the maximum probability value in the probability map of the C2 vertebral disc is determined as the positioning result of the C2 vertebral disc, and a pixel point with the maximum probability value in the probability map of the C3 vertebral disc is determined as the positioning result of the C3 vertebral disc, that is, the positioning result of the C2 vertebral disc and the positioning result of the C3 vertebral disc are respectively determined as the operation results of the C2 vertebral disc and the C3 vertebral disc.
And S240, calculating a similarity value of the operation result and the standard evaluation index based on a preset similarity calculation formula.
And S250, determining the similar value as the evaluation result of the operation result.
It can be understood that, when the similarity value is calculated in the embodiment, only the operation result and the standard evaluation index need to be brought into the preset similarity calculation formula, that is, the evaluation result is only related to the operation result and the standard evaluation index. Compared with the problem that the evaluation result is easily affected by the information during the operation of the evaluation model because the image is input into the evaluation model for evaluation in the prior art, the evaluation result of the embodiment does not depend on the information during the operation of the operation model.
According to the technical scheme provided by the embodiment of the invention, the standard evaluation index and the original volume data of the current object are obtained, the original volume data are input into the operation model which is trained in advance, the operation result is determined according to the output result of the operation model, then the similarity value between the operation result and the standard evaluation index is calculated based on the preset similarity calculation formula, and the similarity value is determined as the evaluation result of the operation result, so that the purpose that the evaluation result does not depend on the information of the operation model in operation can be achieved, and the operation model can adapt to different scenes due to the fact that the operation model is obtained by training through the standard volume data and the standard probability result of different scenes, and the universality of the evaluation method is improved.
EXAMPLE III
Fig. 4 is a schematic structural diagram of an evaluation apparatus according to a third embodiment of the present invention. Referring to fig. 5, the system includes: a first determination module 41, a similarity value calculation module 42 and a second determination module 43.
The first determining module 41 is configured to determine an operation result and a standard evaluation index of a current object; the similarity value calculation module 42 is configured to calculate a similarity value between the operation result and the standard evaluation index based on a preset similarity calculation formula; and a second determining module 43, configured to determine the similarity value as an evaluation result of the operation result.
On the basis of the above technical solutions, the first determining module 41 is further configured to obtain original volume data of the current object;
inputting the original volume data into a pre-trained operation model, and determining an operation result according to an output result of the operation model, wherein the operation model is obtained by training an initial network according to standard volume data and a standard probability result of a current object.
On the basis of the above technical solutions, the first determining module 41 is further configured to determine the number of output channels of the operation model and an output probability map of each channel;
and determining an operation result based on the probability map and a preset probability threshold.
On the basis of the above technical solutions, the first determining module 41 is further configured to obtain a pixel point exceeding a probability threshold in the probability map, and determine the pixel point with the maximum probability value as an operation result.
On the basis of the technical schemes, the standard evaluation index is determined according to the relative position of the relative feature point of the historical object and the pre-established standard feature point, and correspondingly, the operation result comprises the relative position of the target feature point of the current object and the standard feature point.
On the basis of the technical schemes, the standard evaluation index is determined according to the distance between the adjacent characteristic points of the historical object, and correspondingly, the operation result comprises the distance between any two adjacent characteristic points of the current object.
On the basis of the technical schemes, the preset similarity calculation formula is as follows:
Figure BDA0002349843940000101
where α is a normalization coefficient, dis (x, y) is an Euclidean distance calculation formula, i is a label index of the current object, N is the total number of the current object, prediFor the result of the operation of the feature point with index i for the index of the current object, modeliAnd (5) indexing the standard evaluation index of the characteristic point with i for the label of the current object.
The technical scheme provided by the embodiment of the invention determines the operation result and the standard evaluation index of the current object, calculates the similarity value of the operation result and the standard evaluation index based on the preset similarity calculation formula, and determines the similarity value as the evaluation result of the operation result. The problem that in the prior art, evaluation takes more time due to the fact that the reliability of the operation result is judged through comparison of the output results of two algorithms is solved, the purpose that the evaluation result can be obtained through simple calculation according to the operation result and the standard evaluation index is achieved, and the effects of reducing the evaluation time and improving the timeliness are achieved.
Example four
Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 5 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in FIG. 5, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. The memory 28 may include at least one program product having a set of program modules (e.g., the first determining module 41, the similarity value calculating module 42, and the second determining module 43 of the evaluating apparatus) configured to perform the functions of the embodiments of the present invention.
A program/utility 44 having a set of program modules 46 (e.g., first determining module 41, similarity value calculating module 42, and second determining module 43 of the evaluation device) may be stored, for example, in memory 28, such program modules 46 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may include an implementation of a network environment. Program modules 46 generally carry out the functions and/or methodologies of the described embodiments of the invention.
Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with electronic device 12, and/or with any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, to implement an evaluation method provided by an embodiment of the present invention, the method including:
determining an operation result and a standard evaluation index of a current object;
calculating a similarity value of the operation result and a standard evaluation index based on a preset similarity calculation formula;
the similarity value is determined as the evaluation result of the operation result.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, to implement an evaluation method provided by an embodiment of the present invention.
Of course, those skilled in the art will appreciate that the processor may also implement the solution of an evaluation method provided in any embodiment of the present invention.
EXAMPLE five
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements an evaluation method provided in an embodiment of the present invention, where the method includes:
determining an operation result and a standard evaluation index of a current object;
calculating a similarity value of the operation result and a standard evaluation index based on a preset similarity calculation formula;
the similarity value is determined as the evaluation result of the operation result.
Of course, the computer program stored on the computer-readable storage medium provided by the embodiments of the present invention is not limited to the above method operations, and may also perform related operations in an evaluation method provided by any embodiment of the present invention.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device.
The computer-readable signal medium may include computer-readable program code embodied therein for causing a computer to perform the operations, the criteria evaluation index, the evaluation result, and the like. The form of the propagated calculation result, standard evaluation index, evaluation result, and the like. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It should be noted that, in the embodiment of the evaluation apparatus, the included modules are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (10)

1. An evaluation method, comprising:
determining an operation result and a standard evaluation index of a current object;
calculating a similarity value of the operation result and the standard evaluation index based on a preset similarity calculation formula;
and determining the similarity value as an evaluation result of the operation result.
2. The method of claim 1, wherein determining the operation result of the current object comprises:
acquiring original volume data of the current object;
inputting the original volume data into a pre-trained operation model, and determining the operation result according to the output result of the operation model, wherein the operation model is obtained by training an initial network according to the standard volume data and the standard probability result of the current object.
3. The method of claim 2, wherein determining the operation result according to the output result of the operation model comprises:
determining the number of output channels of the operation model and an output probability map of each channel;
and determining the operation result based on the probability map and a preset probability threshold.
4. The method of claim 3, wherein determining the operation result based on the probability map and a preset probability threshold comprises:
and acquiring pixel points exceeding the probability threshold value in the probability map, and determining the pixel point with the maximum probability value as an operation result.
5. The method according to claim 1, wherein the standard evaluation index is determined according to a relative position between a relative feature point of a historical object and a pre-established standard feature point, and accordingly, the operation result comprises a relative position between a target feature point of the current object and the standard feature point.
6. The method according to claim 1, wherein the standard evaluation index is determined according to a distance between adjacent feature points of a historical object, and correspondingly, the operation result comprises a distance between any two adjacent feature points of the current object.
7. The method according to claim 5 or 6, wherein the predetermined similarity calculation formula is:
Figure FDA0002349843930000021
wherein α is a normalization coefficient, dis (x, y) is an Euclidean distance calculation formula, i is a label index of the current object, N is the total number of the current object, prediFor the result of the operation of the feature point with index i for the label of the current object, modeliAnd indexing the standard evaluation index of the characteristic point with the index of i for the label of the current object.
8. An evaluation device, comprising:
the first determination module is used for determining the operation result and the standard evaluation index of the current object;
the similarity value calculation module is used for calculating the similarity value of the operation result and the standard evaluation index based on a preset similarity calculation formula;
and the second determining module is used for determining the similarity value as the evaluation result of the operation result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the evaluation method according to any one of claims 1 to 7 when executing the computer program.
10. A storage medium containing computer-executable instructions, which when executed by a computer processor implement the evaluation method of any one of claims 1-7.
CN201911410488.4A 2019-12-31 2019-12-31 Evaluation method and device, electronic equipment and storage medium Pending CN111179257A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911410488.4A CN111179257A (en) 2019-12-31 2019-12-31 Evaluation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911410488.4A CN111179257A (en) 2019-12-31 2019-12-31 Evaluation method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN111179257A true CN111179257A (en) 2020-05-19

Family

ID=70650658

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911410488.4A Pending CN111179257A (en) 2019-12-31 2019-12-31 Evaluation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111179257A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106951888A (en) * 2017-05-09 2017-07-14 安徽大学 The relative coordinate constrained procedure and localization method of human face characteristic point
CN108171712A (en) * 2016-12-07 2018-06-15 富士通株式会社 The method and apparatus for determining image similarity
CN109118470A (en) * 2018-06-26 2019-01-01 腾讯科技（深圳）有限公司 A kind of image quality evaluating method, device, terminal and server
CN109285153A (en) * 2018-09-29 2019-01-29 广东工业大学 A kind of image quality evaluating method and system
CN109410189A (en) * 2018-10-12 2019-03-01 上海联影智能医疗科技有限公司 The similarity calculating method of image partition method and image, device
CN109658407A (en) * 2018-12-27 2019-04-19 上海联影医疗科技有限公司 Methods of marking, device, server and the storage medium of coronary artery pathological changes
CN109740633A (en) * 2018-12-10 2019-05-10 厦门市美亚柏科信息股份有限公司 A kind of image similarity calculation method, device, storage medium
CN109887016A (en) * 2019-03-25 2019-06-14 北京奇艺世纪科技有限公司 A kind of similarity calculating method and device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108171712A (en) * 2016-12-07 2018-06-15 富士通株式会社 The method and apparatus for determining image similarity
CN106951888A (en) * 2017-05-09 2017-07-14 安徽大学 The relative coordinate constrained procedure and localization method of human face characteristic point
CN109118470A (en) * 2018-06-26 2019-01-01 腾讯科技（深圳）有限公司 A kind of image quality evaluating method, device, terminal and server
CN109285153A (en) * 2018-09-29 2019-01-29 广东工业大学 A kind of image quality evaluating method and system
CN109410189A (en) * 2018-10-12 2019-03-01 上海联影智能医疗科技有限公司 The similarity calculating method of image partition method and image, device
CN109740633A (en) * 2018-12-10 2019-05-10 厦门市美亚柏科信息股份有限公司 A kind of image similarity calculation method, device, storage medium
CN109658407A (en) * 2018-12-27 2019-04-19 上海联影医疗科技有限公司 Methods of marking, device, server and the storage medium of coronary artery pathological changes
CN109887016A (en) * 2019-03-25 2019-06-14 北京奇艺世纪科技有限公司 A kind of similarity calculating method and device

Similar Documents

Publication Publication Date Title
CN109214238B (en) Multi-target tracking method, device, equipment and storage medium
CN112465834B (en) Blood vessel segmentation method and device
US10706534B2 (en) Method and apparatus for classifying a data point in imaging data
CN110176010B (en) Image detection method, device, equipment and storage medium
CN111696089A (en) Arteriovenous determining method, device, equipment and storage medium
CN112132265B (en) Model training method, cup-disk ratio determining method, device, equipment and storage medium
US20120027277A1 (en) Interactive iterative closest point algorithm for organ segmentation
US20170294014A1 (en) Image processing used to estimate abnormalities
CN111145160B (en) Method, device, server and medium for determining coronary artery branches where calcified regions are located
CN110728673A (en) Target part analysis method and device, computer equipment and storage medium
CN112614144A (en) Image segmentation method, device, equipment and storage medium
CN113362314B (en) Medical image recognition method, recognition model training method and device
CN113012114B (en) Blood vessel identification method and device, storage medium and electronic equipment
CN110738643A (en) Method for analyzing cerebral hemorrhage, computer device and storage medium
CN111951276A (en) Image segmentation method and device, computer equipment and storage medium
CN115439453A (en) Vertebral body positioning method and device, electronic equipment and storage medium
US10296810B2 (en) Apparatus and method for determining lesion similarity of medical image
CN113971728B (en) Image recognition method, training method, device, equipment and medium for model
CN113888566B (en) Target contour curve determination method and device, electronic equipment and storage medium
EP3843038B1 (en) Image processing method and system
CN114022614A (en) Method and system for estimating confidence of three-dimensional reconstruction target position
CN112634309B (en) Image processing method, device, electronic equipment and storage medium
CN113537026A (en) Primitive detection method, device, equipment and medium in building plan
CN113379741A (en) Retinal blood vessel segmentation method, device and storage medium based on blood vessel characteristics
CN112530554B (en) Scanning positioning method and device, storage medium and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258

Applicant after: Shanghai Lianying Medical Technology Co., Ltd

Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258

Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd.